metadata
license: apache-2.0
base_model: projecte-aina/roberta-base-ca-v2-cawikitc
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: p1
results: []
pipeline_tag: zero-shot-classification
p1
This model is a fine-tuned version of projecte-aina/roberta-base-ca-v2-cawikitc on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8254
- Accuracy: 0.5
- Precision: 0.25
- Recall: 0.5
- F1: 0.3333
- Ratio: 1.0
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 2
- seed: 47
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- lr_scheduler_warmup_steps: 4
- num_epochs: 2
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Ratio |
|---|---|---|---|---|---|---|---|---|
| 0.8263 | 0.38 | 10 | 0.8199 | 0.5 | 0.5 | 0.5 | 0.3473 | 0.0163 |
| 0.8283 | 0.75 | 20 | 0.8389 | 0.5 | 0.25 | 0.5 | 0.3333 | 1.0 |
| 0.8167 | 1.13 | 30 | 0.8325 | 0.5 | 0.25 | 0.5 | 0.3333 | 1.0 |
| 0.8183 | 1.51 | 40 | 0.8228 | 0.4973 | 0.2493 | 0.4973 | 0.3321 | 0.9973 |
| 0.8178 | 1.89 | 50 | 0.8254 | 0.5 | 0.25 | 0.5 | 0.3333 | 1.0 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2